Zhiyuan Zhang

10

Papers

6

Total Citations

Papers (10)

BHViT: Binarized Hybrid Vision Transformer

GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation

I2V3D: Controllable Image-to-video Generation with 3D Guidance

Information-Bottleneck Driven Binary Neural Network for Change Detection

Scaling Up Dynamic Human-Scene Interaction Modeling

Context-Aware Video Reconstruction for Rolling Shutter Cameras

ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics

Full-Body Articulated Human-Object Interaction

Understanding and Improving Layer Normalization

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense